Hi everyone,
I’m currently encountering a 503 Service Unavailable error when calling the Gemini API (model: gemini-3-flash-agent).
Error details:
-
Status: 503 UNAVAILABLE
-
Reason: MODEL_CAPACITY_EXHAUSTED
-
Message: “No capacity available for model gemini-3-flash-agent on the server”
I’ve tried switching accounts, but the issue still persists, so it doesn’t seem to be account-related.
Has anyone else experienced this issue?
Is this due to server overload, or is there something I can do on my end to mitigate it?
Any suggestions (e.g., retry strategies, alternative models, or configuration changes) would be greatly appreciated.
Thanks in advance!